| """Génère PDF minimaux lisibles par pypdf + seed SQLite.""" |
| from __future__ import annotations |
|
|
| import sys |
| from pathlib import Path |
|
|
| ROOT = Path(__file__).resolve().parents[1] |
| sys.path.insert(0, str(ROOT)) |
|
|
| from pypdf import PdfReader |
|
|
| from app.core.config import get_settings |
| from app.sql.seed import seed_company_db |
|
|
|
|
| def _esc(text: str) -> str: |
| return ( |
| text.replace("\\", "\\\\") |
| .replace("(", "\\(") |
| .replace(")", "\\)") |
| ) |
|
|
|
|
| def write_simple_pdf(path: Path, title: str, body: str) -> None: |
| lines = [title, ""] |
| for para in body.splitlines(): |
| while len(para) > 88: |
| lines.append(para[:88]) |
| para = para[88:] |
| lines.append(para) |
| safe = [ |
| line.encode("latin-1", "replace").decode("latin-1") |
| for line in lines[:70] |
| ] |
|
|
| content = ["BT", "/F1 10 Tf", "40 780 Td", "12 TL"] |
| first = True |
| for line in safe: |
| if not first: |
| content.append("T*") |
| content.append(f"({_esc(line)}) Tj") |
| first = False |
| content.append("ET") |
| stream = "\n".join(content).encode("latin-1") |
|
|
| objects = [ |
| b"1 0 obj<< /Type /Catalog /Pages 2 0 R >>endobj\n", |
| b"2 0 obj<< /Type /Pages /Kids [3 0 R] /Count 1 >>endobj\n", |
| ( |
| b"3 0 obj<< /Type /Page /Parent 2 0 R " |
| b"/MediaBox [0 0 612 792] /Contents 4 0 R " |
| b"/Resources << /Font << /F1 5 0 R >> >> >>endobj\n" |
| ), |
| ( |
| f"4 0 obj<< /Length {len(stream)} >>stream\n".encode("ascii") |
| + stream |
| + b"\nendstream\nendobj\n" |
| ), |
| b"5 0 obj<< /Type /Font /Subtype /Type1 /BaseFont /Helvetica >>endobj\n", |
| ] |
|
|
| out = bytearray(b"%PDF-1.4\n") |
| offsets = [0] |
| for obj in objects: |
| offsets.append(len(out)) |
| out.extend(obj) |
| xref = len(out) |
| out.extend(f"xref\n0 {len(offsets)}\n".encode("ascii")) |
| out.extend(b"0000000000 65535 f \n") |
| for off in offsets[1:]: |
| out.extend(f"{off:010d} 00000 n \n".encode("ascii")) |
| out.extend( |
| ( |
| f"trailer<< /Size {len(offsets)} /Root 1 0 R >>\n" |
| f"startxref\n{xref}\n%%EOF\n" |
| ).encode("ascii") |
| ) |
| path.write_bytes(out) |
|
|
|
|
| def main() -> None: |
| pairs = [ |
| ( |
| ROOT / "data/policies/refund_policy.md", |
| ROOT / "data/policies/refund_policy.pdf", |
| ), |
| ( |
| ROOT / "data/reports/profitability_report.md", |
| ROOT / "data/reports/profitability_report.pdf", |
| ), |
| ] |
| for src, dst in pairs: |
| text = src.read_text(encoding="utf-8") |
| write_simple_pdf(dst, src.stem, text) |
| reader = PdfReader(str(dst)) |
| extracted = "".join( |
| (page.extract_text() or "") for page in reader.pages |
| ) |
| print(f"PDF ok {dst.name}: {len(extracted)} chars") |
|
|
| get_settings.cache_clear() |
| db = seed_company_db(ROOT / "data/database/company.db", ROOT / "data") |
| print(f"DB ok {db} ({db.stat().st_size} octets)") |
|
|
|
|
| if __name__ == "__main__": |
| main() |
|
|
